AI/ML Engineer

About The Opportunity

• Design, implement and validate end-to-end ML solutions—data ingestion ➜ feature engineering ➜ model training ➜ optimized inference—for avionics and operations use-cases.
• Develop production-quality Python code and deep-learning models (PyTorch/TensorFlow) for computer vision, time-series, or NLP tasks relevant to aviation telemetry.
• Package and deploy models using containerisation and CI/CD pipelines; ensure low-latency, reliable inference in on-premise or cloud environments.
• Collaborate with systems engineers to integrate ML into sensor stacks and real-time pipelines; contribute to model validation, calibration and edge deployment strategies.
• Build monitoring, alerting and A/B evaluation frameworks to track model performance, drift and data-quality in production.
• Create reproducible experiments, maintain model versioning and produce clear documentation to support cross-functional teams and certification processes.
  

Skills & Qualifications

• 3+ years experience building and deploying ML/DL models in production with strong Python expertise.
• Hands-on with PyTorch or TensorFlow and practical knowledge of CNNs, RNNs, or Transformer architectures.
• Experience with data pipelines (ETL), SQL/NoSQL, and feature engineering for sensor/time-series data.
• Proven experience containerizing workloads (Docker) and integrating models into CI/CD pipelines.
• Familiarity with MLOps practices: monitoring, model-versioning, retraining triggers and logging.
• Comfort working on-site in India and collaborating with cross-functional hardware/system teams.
  

Preferred

• Experience with real-time/edge inference optimisations, quantization or TensorRT/ONNX.
• Background in computer vision for aerial imagery, sensor fusion, or NLP for operational text streams.
• Exposure to cloud ML services (AWS/GCP/Azure) and orchestration (Kubernetes).
• Familiarity with avionics standards, safety-critical software lifecycle, or certification processes.
  

• Work on mission-critical AI systems with direct operational impact in aviation technology.
• Collaborative, engineering-first environment with clear ownership and fast decision cycles.
• Opportunities for skill growth across ML, embedded systems and MLOps in a high-growth domain.